Unidir_Get#

This is the benchmark for the MPI_Get

Unidir_Get Definition#

Property

Description

Measured pattern

As symbolized between image0 in the figure below. This benchmark runs on two active processes (Q=2).

MPI routine

MPI_Get

MPI data type

MPI_BYTE, for both origin and target

Reported timings

t=t(M) (in μsec) as indicated in the figure below, non-aggregate (M=1)and aggregate (M=n_sample). For details, see Actual Ben chmarking.

Reported throughput

X/t, aggregate and non-aggregate

Unidir_Get Pattern#

../_images/image08.png